Adversarial 3D Virtual Patches using Integrated Gradients

Chengzeng You, Zhongyuan Hau, Binbin Xu, Soteris Demetriou
6/1/2024
cs.CVcs.CR

No confident code implementation found for this paper.

Abstract

LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of reducing the required spoofing area through a novel object-hiding strategy based on virtual patches (VPs). We first manually design VPs (MVPs) and show that VP-focused attacks can achieve similar success rates with prior work but with a fraction of the required spoofing area. Then we design a framework Saliency-LiDAR (SALL), which can identify critical regions for LiDAR objects using Integrated Gradients. VPs crafted on critical regions (CVPs) reduce object detection recall by at least 15% compared to our baseline with an approximate 50% reduction in the spoofing area for vehicles of average size.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Navigating Threats: A Survey of Physical Adversarial Attacks on LiDAR Perception Systems in Autonomous Vehicles

84% match2024

ControlLoc: Physical-World Hijacking Attack on Visual Perception in Autonomous Driving

84% match2024

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

83% match2024

BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection

82% match2024

Experimental Validation of Sensor Fusion-based GNSS Spoofing Attack Detection Framework for Autonomous Vehicles

82% match2024

OBJVanish: Physically Realizable Text-to-3D Adv. Generation of LiDAR-Invisible Objects

82% match2025

Cite this paper

@article{you2024adversarial,
  title  = {Adversarial 3D Virtual Patches using Integrated Gradients},
  author = {Chengzeng You and Zhongyuan Hau and Binbin Xu and Soteris Demetriou},
  year   = {2024},
  eprint = {2406.00282},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.00282v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.00282.svg)](https://codeofpaper.com/paper/2406.00282)

Discussion